# Claude Desktop > Point managed Claude Desktop on 3P at ScaleMax using its supported Gateway configuration. > This guide is for **Claude Desktop on third-party (3P)**, Anthropic's managed deployment mode. It does not replace the provider for a normal consumer Claude.ai account or its hosted chats. Choose the tab that matches the type of ScaleMax key you created; the correct base URL is different for API-credit and Claude-token keys. ## Requirements Use a Claude Desktop version that includes third-party inference and a deployment where you are allowed to apply a local 3P configuration or distribute managed settings. The gateway supports streaming and tool use on `POST /v1/messages`, local input estimates on `POST /v1/messages/count_tokens`, and authenticated model discovery on `GET /v1/models`. For an API-credit ScaleMax key ## API Credit setup Use this route when the key is funded with API credits. Claude Desktop sends Anthropic Messages requests through the standard ScaleMax gateway. ### 1\. Open Claude Desktop's 3P configuration 1. In Claude Desktop, open **Help → Troubleshooting → Enable Developer Mode**, then choose **Developer → Configure third-party inference**. 2. For one Windows or macOS machine, enter the settings below and choose **Apply locally**. 3. For managed devices, use **Export** from that screen. Deploy the exported `.reg` on Windows, `.mobileconfig` on macOS, or bootstrap JSON with your device-management tool. Do not hand-edit Claude Desktop's internal files. This guide applies only to Claude Desktop's managed third-party inference (3P) mode. It does not configure normal consumer Claude.ai chats, and Claude Desktop does not read Claude Code's settings or environment variables. ### 2\. Enter these connection settings - **Inference provider:** Gateway - **Gateway base URL:** `https://api.scalemax.pro` - **Credential kind:** Static API key - **Gateway API key:** `YOUR_SCALEMAX_API_KEY` — use the API-credit key created for this user or device. - **Gateway auth scheme:** Bearer **Key compatibility:** The API-credit key must include Claude provider access. A key restricted to OpenAI cannot populate Claude models in Desktop. > **Use the origin exactly as shown.** Do not append `/v1`; Claude Desktop adds the Anthropic API path itself. For this selection, requests resolve to `https://api.scalemax.pro/v1/messages`. ### 3\. Keep model discovery enabled Leave discovery on so Claude Desktop authenticates to `https://api.scalemax.pro/v1/models` with the same Bearer key and populates its model picker. The current Claude IDs are: - `claude-haiku-4-5-20251001` - `claude-haiku-5-5` - `claude-opus-4-6` - `claude-opus-4-7` - `claude-opus-4-8` - `claude-opus-5` - `claude-opus-5-5` - `claude-sonnet-5` - `claude-sonnet-5-5` - `fable-5` If your organization requires a fixed model list, export the settings from Claude Desktop after discovery succeeds; use the export's encoding for managed policy values. ### 4\. Review the managed configuration values The configuration screen validates and exports these logical values. The API key remains a static Bearer credential; do not replace it with a browser login token. credit-mode-gateway.json: ```json { "inferenceProvider": "gateway", "inferenceGatewayBaseUrl": "https://api.scalemax.pro", "inferenceGatewayApiKey": "YOUR_SCALEMAX_API_KEY", "inferenceCredentialKind": "static", "inferenceGatewayAuthScheme": "bearer", "coworkEgressAllowedHosts": ["*"], "toolSearchEnabled": true } ``` ### 5\. Verify with one small request Before opening a Desktop chat, use this one-token probe. It verifies the selected gateway route and key without sending a long prompt. **macOS / Linux** credit-mode-check.sh: ```bash export SCALEMAX_API_KEY="YOUR_SCALEMAX_API_KEY" curl -sS "https://api.scalemax.pro/v1/messages" \ -H "Authorization: Bearer $SCALEMAX_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-haiku-4-5-20251001", "max_tokens": 1, "messages": [{"role": "user", "content": "K"}] }' ``` **Windows PowerShell** credit-mode-check.ps1: ```powershell $env:SCALEMAX_API_KEY = "YOUR_SCALEMAX_API_KEY" @' { "model": "claude-haiku-4-5-20251001", "max_tokens": 1, "messages": [{"role": "user", "content": "K"}] } '@ | Set-Content -Path body.json curl.exe -sS "https://api.scalemax.pro/v1/messages" ` -H "Authorization: Bearer $env:SCALEMAX_API_KEY" ` -H "anthropic-version: 2023-06-01" ` -H "content-type: application/json" ` --data-binary "@body.json" ``` PowerShell changes quotes inside a JSON argument, so the request body goes into body.json first and curl.exe sends that file. Type curl.exe, not curl: in Windows PowerShell 5.1, curl is a different command. Then fully quit and reopen Claude Desktop. Confirm it starts in 3P mode, the model picker includes the discovered ScaleMax Claude models, and a short test message succeeds. ### Troubleshooting this mode - **401 or invalid credential:** confirm the key is active, paste it without spaces or quotes, and use API Credit with `https://api.scalemax.pro`. Do not post the key in screenshots or support messages. - **404 or rejected gateway URL:** remove `/v1` from the base URL field. The field takes the origin, not the Messages endpoint. - **No models in the picker:** fully quit and reopen Desktop, verify that `https://api.scalemax.pro/v1/models` is reachable with the same key, and check whether an MDM policy is overriding local settings. - **Local settings do not stick:** use the app's Export action and have your Windows or macOS management policy install the generated artifact. - **Allowance unavailable:** If the API-credit balance is depleted, add API credits or use a different active API-credit key. A Claude-token key cannot be used on this route. For a Claude-token ScaleMax key ## API Token setup Use this route when the key has a Claude token allowance. Claude Desktop sends the same Anthropic Messages requests through the token gateway. ### 1\. Open Claude Desktop's 3P configuration 1. In Claude Desktop, open **Help → Troubleshooting → Enable Developer Mode**, then choose **Developer → Configure third-party inference**. 2. For one Windows or macOS machine, enter the settings below and choose **Apply locally**. 3. For managed devices, use **Export** from that screen. Deploy the exported `.reg` on Windows, `.mobileconfig` on macOS, or bootstrap JSON with your device-management tool. Do not hand-edit Claude Desktop's internal files. This guide applies only to Claude Desktop's managed third-party inference (3P) mode. It does not configure normal consumer Claude.ai chats, and Claude Desktop does not read Claude Code's settings or environment variables. ### 2\. Enter these connection settings - **Inference provider:** Gateway - **Gateway base URL:** `https://api.scalemax.pro/token` - **Credential kind:** Static API key - **Gateway API key:** `YOUR_SCALEMAX_API_KEY` — use the Claude-token key created for this user or device. - **Gateway auth scheme:** Bearer **Key compatibility:** Only a Claude token-pack or Claude-scoped token key is compatible with Claude Desktop. An OpenAI token-pack key is not compatible with this Anthropic Messages gateway. > **Use the origin exactly as shown.** Do not append `/v1`; Claude Desktop adds the Anthropic API path itself. For this selection, requests resolve to `https://api.scalemax.pro/token/v1/messages`. ### 3\. Keep model discovery enabled Leave discovery on so Claude Desktop authenticates to `https://api.scalemax.pro/token/v1/models` with the same Bearer key and populates its model picker. The current Claude IDs are: - `claude-haiku-4-5-20251001` - `claude-haiku-5-5` - `claude-opus-4-6` - `claude-opus-4-7` - `claude-opus-4-8` - `claude-opus-5` - `claude-opus-5-5` - `claude-sonnet-5` - `claude-sonnet-5-5` - `fable-5` If your organization requires a fixed model list, export the settings from Claude Desktop after discovery succeeds; use the export's encoding for managed policy values. ### 4\. Review the managed configuration values The configuration screen validates and exports these logical values. The API key remains a static Bearer credential; do not replace it with a browser login token. token-mode-gateway.json: ```json { "inferenceProvider": "gateway", "inferenceGatewayBaseUrl": "https://api.scalemax.pro/token", "inferenceGatewayApiKey": "YOUR_SCALEMAX_API_KEY", "inferenceCredentialKind": "static", "inferenceGatewayAuthScheme": "bearer", "coworkEgressAllowedHosts": ["*"], "toolSearchEnabled": true } ``` ### 5\. Verify with one small request Before opening a Desktop chat, use this one-token probe. It verifies the selected gateway route and key without sending a long prompt. **macOS / Linux** token-mode-check.sh: ```bash export SCALEMAX_API_KEY="YOUR_SCALEMAX_API_KEY" curl -sS "https://api.scalemax.pro/token/v1/messages" \ -H "Authorization: Bearer $SCALEMAX_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-haiku-4-5-20251001", "max_tokens": 1, "messages": [{"role": "user", "content": "K"}] }' ``` **Windows PowerShell** token-mode-check.ps1: ```powershell $env:SCALEMAX_API_KEY = "YOUR_SCALEMAX_API_KEY" @' { "model": "claude-haiku-4-5-20251001", "max_tokens": 1, "messages": [{"role": "user", "content": "K"}] } '@ | Set-Content -Path body.json curl.exe -sS "https://api.scalemax.pro/token/v1/messages" ` -H "Authorization: Bearer $env:SCALEMAX_API_KEY" ` -H "anthropic-version: 2023-06-01" ` -H "content-type: application/json" ` --data-binary "@body.json" ``` PowerShell changes quotes inside a JSON argument, so the request body goes into body.json first and curl.exe sends that file. Type curl.exe, not curl: in Windows PowerShell 5.1, curl is a different command. Then fully quit and reopen Claude Desktop. Confirm it starts in 3P mode, the model picker includes the discovered ScaleMax Claude models, and a short test message succeeds. ### Troubleshooting this mode - **401 or invalid credential:** confirm the key is active, paste it without spaces or quotes, and use API Token with `https://api.scalemax.pro/token`. Do not post the key in screenshots or support messages. - **404 or rejected gateway URL:** remove `/v1` from the base URL field. The field takes the origin, not the Messages endpoint. - **No models in the picker:** fully quit and reopen Desktop, verify that `https://api.scalemax.pro/token/v1/models` is reachable with the same key, and check whether an MDM policy is overriding local settings. - **Local settings do not stick:** use the app's Export action and have your Windows or macOS management policy install the generated artifact. - **Allowance unavailable:** If the Claude token allowance is exhausted, renew or replace it with an active Claude-token key. An API-credit key cannot be used on this route. ## Web access, search and connectors in Cowork `coworkEgressAllowedHosts` controls which sites Cowork may reach. While it is unset or empty, Cowork and Chat refuse every Web Fetch and the sandbox shell cannot download anything, so the configuration above sets it to `["*"]`. List specific domains instead if your organisation needs a tighter allowlist. `toolSearchEnabled` loads connector tools on demand, so many connectors do not fill the context window. Web Search works through the ScaleMax gateway on every model: ScaleMax runs the search and returns real results with links. No search key or extra configuration is needed. Connectors that Anthropic hosts itself (marked "Made by Anthropic" in the connector directory, such as the claude.ai Gmail, Google Drive and Google Calendar connectors) are only available when signed in to claude.ai, so they do not appear in third-party mode on any gateway. Other connectors work: add remote MCP servers through the `managedMcpServers` configuration key or a plugin that bundles them, and local MCP servers from **Settings → Developer**. For Google Workspace, use [Google's own Workspace MCP servers](https://developers.google.com/workspace/guides/configure-mcp-servers). ## Enable safe GitHub skill tools Third-party inference configures the model connection, but it does not automatically grant the desktop app network or filesystem tools. Install ScaleMax's bounded GitHub MCP after the gateway is working: **macOS / Linux** ```bash npm install -g scalemax@latest scalemax claude-tools ``` **Windows PowerShell** ```powershell npm.cmd install -g scalemax@latest scalemax.cmd claude-tools ``` Windows PowerShell blocks npm’s .ps1 launchers by default (“running scripts is disabled on this system”), so these commands use the .cmd launcher: npx.cmd, npm.cmd, scalemax.cmd. In Command Prompt you can leave out .cmd. Restart Claude Desktop, then use **Cowork** or **Code**. The normal Chat tab does not expose local tools. Claude will receive `github_fetch`, `github_tree`, and `github_install_skill`. > The MCP accepts only public GitHub HTTPS hosts, limits response and archive sizes, rejects unsafe paths and symlinks, refuses to overwrite existing skills, and writes only below `~/Claude/skills`. It does not grant a general shell, arbitrary URL access, or unrestricted filesystem access. **Review the repository before installing.** A `SKILL.md` is instruction content that Claude may follow; the bridge does not execute repository code, but trusted source is still required. You can request, for example: `Install the template skill from anthropics/skills on GitHub`. Claude must ask for confirmation before the write-capable install tool runs. ## Keep the key private > The desktop configuration contains a long-lived credential. Do not share the exported profile publicly or check it into source control. Use a separate per-user or per-device ScaleMax key where possible so it can be revoked independently. See [Claude Desktop's official LLM gateway guide](https://claude.com/docs/third-party/claude-desktop/gateway) and [in-app configuration guide](https://claude.com/docs/third-party/claude-desktop/in-app-configuration) for deployment details.